FaceBERT: Face De-Identification Using VQGAN and BERT.
ICTC(2022)
摘要
This paper presents FaceBERT, a face de-identification technique based on image generation to solve the infringement of portrait rights. Using the VQGAN model, it learns a quantized codebook that expresses an image in block units, encodes the image using the codebook, and then trains the BERT model. As a result of an experiment using FFHQ and CelebA-HQ, it was confirmed that the face images generated using FaceBERT were natural de-identified face images and different from the originals.
更多查看译文
关键词
FaceBERT,VQGAN,BERT,face de-identification
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要